Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare the safety profile (destructive, idempotent, open-world), and the description adds behavior beyond that: approval is recorded before AP2 and escrow funding, there is no immediate treasury release, and exact retries reuse saved requests and 'cannot replace consent or create a second payment.' It also states the auth requirement (X-Wever-Agent-Key), which no annotation conveys.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Each sentence adds a distinct constraint (consent rules, side-effect ordering, retry semantics, auth), and the primary purpose is front-loaded. It is dense and long, but there is little that could be dropped without losing a real constraint.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, money-moving tool with a nested object, no output schema, and 0% schema coverage, the description covers purpose, caller eligibility, consent validity, side-effect ordering, idempotency, and auth. It stops short of describing failure modes or the state returned after execution, leaving a small residual gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description carries the burden and mostly succeeds, giving meaning to every nested customer_approval field (quote_sha256 as the saved quote hash, amount_atomic as six-decimal USDC, currency USD, approval_text from the quote, approved_at as Unix seconds, stable approval_id). The one gap is intent_id itself, whose role is only implied rather than described.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence states a specific verb+resource+condition: 'Execute a purchase after customer approval, without merchant review.' This cleanly separates it from siblings like wever_purchase-create-intent (which creates the intent) and wever_purchase-status (which only reads state). An agent can select it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly routes by caller type: delegated customer agents may supply customer_approval attesting human consent, while 'Other agents require the human review page.' It also states when to omit the field ('to retry an already approved intent') and draws a hard boundary: 'Never supply consent before the human approves.' This is complete when/when-not/alternative guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.